检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Yu, Ting Lin, Xiaojun Wang, Shuhui Sheng, Weiguo Huang, Qingming Yu, Jun School of Information Science and Technology Hangzhou Normal University Hangzhou311121 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing101408 China Key Laboratory of Complex Systems Modeling and Simulation School of Computer Science and Technology Hangzhou Dianzi University Hangzhou310018 China

Three-Dimensional (3D) dense captioning is an emerging vision-language bridging task that aims to generate multiple detailed and accurate descriptions for 3D scenes. It presents significant potential and challenges due to its closer representation of the real world compared to 2D visual captioning, as well as complexities in data collection and processing of 3D point cloud sources. Despite the popularity and success of existing methods, there is a lack of comprehensive surveys summarizing the advancements in this field, which hinders its progress. In this paper, we provide a comprehensive review of 3D dense captioning, covering task definition, architecture classification, dataset analysis, evaluation metrics, and in-depth prosperity discussions. Based on a synthesis of previous literature, we refine a standard pipeline that serves as a common paradigm for existing methods. We also introduce a clear taxonomy of existing models, summarize technologies involved in different modules, and conduct detailed experiment analysis. Instead of a chronological order introduction, we categorize the methods into different classes to facilitate exploration and analysis of the differences and connections among existing techniques. We also provide a reading guideline to assist readers with different backgrounds and purposes in reading efficiently. Furthermore, we propose a series of promising future directions for 3D dense captioning by identifying challenges and aligning them with the development of related tasks, offering valuable insights and inspiring future research in this field. Our aim is to provide a comprehensive understanding of 3D dense captioning, foster further investigations, and contribute to the development of novel applications in multimedia and related domains. Copyright © 2024, The Authors. All rights reserved.

关键词： Data handling

来源：评论

学校读者我要写书评

暂无评论

Prompting Video-Language Foundation Models with Domain-specific Fine-grained Heuristics for Video Question Answering

arXiv

引用

arXiv 2024年

作者： Yu, Ting Fu, Kunhao Wang, Shuhui Huang, Qingming Yu, Jun School of Information Science and Technology Hangzhou Normal University Hangzhou311121 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing101408 China Key Laboratory of Complex Systems Modeling and Simulation School of Computer Science and Technology Hangzhou Dianzi University Hangzhou310018 China

Video Question Answering (VideoQA) represents a crucial intersection between video understanding and language processing, requiring both discriminative unimodal comprehension and sophisticated cross-modal interaction for accurate inference. Despite advancements in multi-modal pre-trained models and video-language foundation models, these systems often struggle with domain-specific VideoQA due to their generalized pre-training objectives. Addressing this gap necessitates bridging the divide between broad cross-modal knowledge and the specific inference demands of VideoQA tasks. To this end, we introduce HeurVidQA, a framework that leverages domain-specific entity-action heuristics to refine pre-trained video-language foundation models. Our approach treats these models as implicit knowledge engines, employing domain-specific entity-action prompters to direct the model’s focus toward precise cues that enhance reasoning. By delivering fine-grained heuristics, we improve the model’s ability to identify and interpret key entities and actions, thereby enhancing its reasoning capabilities. Extensive evaluations across multiple VideoQA datasets demonstrate that our method significantly outperforms existing models, underscoring the importance of integrating domain-specific knowledge into video-language models for more accurate and context-aware VideoQA. Copyright © 2024, The Authors. All rights reserved.

关键词： Inference engines

来源：评论

学校读者我要写书评

暂无评论

FedAG:A Federated Learning Method Based on Data Importance Weighted Aggregation

FedAG:A Federated Learning Method Based on Data Importance W...

引用

IEEE International Conference on Communications in China (ICCC)

作者： Mengchu Xu Yan Zeng Meiting Xue Ji-Lin Zhang Jian Wan Mingyao Zhou Yilin Wen Yukun Shi School of Computer Science and Technology Hangzhou Dianzi University Hangzhou China Key Laboratory of Complex Systems Modeling and Simulation Ministry of Education Hangzhou China Zhejiang Engineering Research Center of Data Security Governance Hangzhou China School of Cyberspace Hangzhou Dianzi University Hangzhou China Huawei Enterprise Communication Technology Co Hangzhou China

Federated learning is a distributed machine learning approach that trains models with multiple clients and data locally. However, the existing methods ignore the differences between local models caused by the data heterogeneity, and give a high aggregation weight for the low-quality local model, which leads to low accuracy of the global model. For this problem, we propose a federated learning method based on data importance weighted aggregation, FedAG. It constructs an evaluation model of data importance based on the data distribution skewness, data volume, and data quality of clients, and aggregates local models with different weights computed by the evaluation model of data importance into a global model. We make experiments on five datasets including EMNIST, MNIST, and CIFAR-10. The results show that the accuracy of FedAG is respectively improved by 6.5%, 1.8%, 1.3% and 2.1%, compared with FedAvg, FedProx, FedVar, and Scaffold algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Grand-canonical Monte-Carlo simulation of solutions of salt mixtures: theory and implementation

arXiv

引用

arXiv 2017年

作者： Nguyen, Toan T. VNU Key Laboratory"Multiscale Simulation of Complex Systems" Faculty of Physics VNU University of Science Vietnam National University 334 Nguyen Trai Street Thanh Xuan Hanoi School of Physics Georgia Institute of Technology 837 State Street AtlantaGA30332-0430 United States

A Grand-canonical Monte-Carlo simulation method extended to simulate a mixture of salts is presented. Due to charge neutrality requirement of electrolyte solutions, ions must be added to or removed from the system in groups. This leads to some complications compared to regular Grand Canonical simulation. Here, a recipe for simulation of electrolyte solution of salt mixture is presented. It is then implemented to simulate solution of 1:1, 2:1 and 2:2 salts or their mixtures at different concentrations using the primitive ion model. The osmotic pressures of the electrolyte solutions are calculated and shown to depend linearly on the salt concentrations within the concentration range simulated. We also show that at the same concentration of divalent anions, the presence of divalent cations make it easier to insert monovalent cations into the system. This can explain some quantitative differences observed in experiments of the MgCl2 salt mixture and MgSO4 salt mixture. Copyright © 2017, The Authors. All rights reserved.

关键词： Magnesium compounds

来源：评论

学校读者我要写书评

暂无评论

Mitigating Over-Trust in Chat Companion Robot Interaction Using Augmented Reality 23

Mitigating Over-Trust in Chat Companion Robot Interaction Us...

引用

Proceedings of the 4th International Conference on Artificial Intelligence and Computer Engineering

作者： Guobao Wang Changshun Zhao Ying Liu Di He Yuqing Wang Kaiyue Zhang Yanshan University/Jiangsu Xuzhou Construction Machinery Group Co. Ltd. China Officers College of PAP China National Key Laboratory for Complex Systems Simulation China University of Electronic Science and Technology of China China Jiangsu Province Tongshan Secondary Vocational School China

ISBN: (纸本)9798400708831

This study aims to explore the effects of different human-machine interfaces, system performance, and robot interaction modalities on over-trust in chat companion robot systems. We designed and implemented three types of interfaces: 2D Virtual Interface + Virtual Robot, 3D Augmented Reality Interface + AR-based Virtual Robot, and 3D Real World + NAO Physical Robot. We also manipulated the system performance (high or low) and the robot interaction modality (language, gesture, or both). We conducted a user study with 30 participants, who interacted with the chat companion robot under different conditions and rated their trust, distrust, and human-robot distance. We also measured the user experience in terms of usefulness and ease of use. The results showed that the type of interface significantly influenced the trust, distrust, and human-robot distance of the users, and that the 3D augmented reality interface was the most effective in enhancing trust and reducing distrust and distance. The performance of the system also affected the trust and distance of the users, and the gesture interface was the most sensitive to the performance variation. The modality of the interaction did not have a significant impact on the dependent variables. The user experience ratings also indicated that the 3D augmented reality interface was the most useful and easy to use. The implications and limitations of these findings are discussed in the paper.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Stochastic model predictive control based economic dispatch for hybrid energy system including wind and energy storage devices

Stochastic model predictive control based economic dispatch ...

引用

IEEE Symposium Series on Computational Intelligence

作者： Yan Zhang Rui Wang Tao Zhang Tianjun Liao Yajie Liu Bo Guo College of Information Systems and Management National University of Defense Technology State key Laboratory of Complex System Simulation Beijing Institute of System Engineering

ISBN: (纸本)9781479975617

In this paper, a stochastic model predictive control (SMPC) approach is proposed to schedule a hybrid energy system (HES) which composes a battery energy storage system (BESS) and a wind farm. The SMPC is used to control the charge and discharge of the BESS to minimize the operation costs and maximum the selling power revenue for the HES owner with considering wind production and electricity price forecast uncertainties. Case study is employed to assess the performance of the SMPC approach and simulation results show that this approach proposed in this paper is effective and feasible.

关键词： ENERGY systems Energy storage devices Wind SMPC Predictive control Stochastic models battery energy storage system Hetastarch Dispatching

来源：评论

学校读者我要写书评

暂无评论

Asymptotic critical behavior of holographic phase transition at finite topological charge - the spectrum of excited states becomes continuous at T = 0

arXiv

引用

arXiv 2021年

作者： Nguyen, Toan T. Phat, Tran Huu Key Laboratory for Multiscale Simulation of Complex Systems Department of Theoretical Physics University of Science Vietnam National University – Hanoi 334 Nguyen Trai street Thanh Xuan Hanoi100000 Viet Nam Vietnam Atomic Energy Commission 59 Ly Thuong Kiet street Hoan Kiem Hanoi100000 Viet Nam

Within the framework of AdS/CFT duality, excited states of the conformal field living at the global AdS boundary of a four-dimensional spacetime Einstein gravity are investigated analytically in the probe limit where the field equations are linearized. At asymptotically large values, the threshold chemical potential for the appearance of excited condensate states are discrete, equal spacing, with the gap approaches zero logarithmically in the limit T → 0. Remarkably, numerical results show that, this behavior applies even for states as low as for the first or the second excited state of the condensate. This is especially significant on the liquid side of the black hole van der Waals - like phase transition (small or zero topological charge) where there seems to be no gap between the ground state and the first excited state at zero temperature. We postulate that, at the exact limit T = 0 where the gap is zero, the spectrum of threshold chemical potentials becomes continuous, all excited states of the condensate are activated above a finite chemical potential, suggesting a new quantum phase transition as a function of the chemical potential. Previous studies have largely missed this continuous spectrum of excited states in the T → 0 limit. This fact should be taken into account carefully in AdS/CFT duality studies. Copyright © 2021, The Authors. All rights reserved.

关键词： Excited states

来源：评论

学校读者我要写书评

暂无评论

On the triplet of holographic phase transition

arXiv

引用

arXiv 2021年

作者： Phat, Tran Huu Nguyen, Toan T. Vietnam Atomic Energy Commission 59 Ly Thuong Kiet street Hoan Kiem Hanoi100000 Viet Nam Key Laboratory for Multiscale Simulation of Complex Systems Department of Theoretical Physics University of Science Vietnam National University − Hanoi 334 Nguyen Trai street Thanh Xuan Hanoi100000 Viet Nam

We start from an Einstein − Maxwell system coupled with a charged scalar field in Anti−de Sitter space−time. In the setup where the pressure P is identified with the cosmological constant, the AdS black hole (BH) undergoes the phase transition from small to large BHs, which is similar to the transition from liquid to gas in the van der Waals theory. Based on this framework, we study the triplet of holographic superconducting states, consisting of ground state and two lowest excited states. Our numerical calculations show that the pressure variation in the bulk creates a mechanism in the boundary which causes changes in the physical properties of excited states, namely: a) when the pressure P is higher than the critical pressure Pc (P > Pc) of the phase transition from small to large BHs the ground state and the first excited state are superconducting states while the second excited state is the normal one. However, at lower pressure, P ≤ Pc, the ground state is solely the superconducting state. We conjecture that the precedent phenomena could take place when the scalar field in the bulk is replaced by other matter fields. Copyright © 2021, The Authors. All rights reserved.

关键词： Ground state

来源：评论

学校读者我要写书评

暂无评论

A Survey of Knowledge Enhanced Pre-trained Language Models

引用

ACM Transactions on Asian and Low-Resource Language Information Processing 1000年

作者： Jian Yang Xinyu Hu Gang Xiao Yulong Shen Computer Science and Technology Xidian University Xi’an China National Key Laboratory for Complex Systems Simulation Beijing China

Pre-trained language models learn informative word representations on a large-scale text corpus through self-supervised learning, which has achieved promising performance in fields of natural language processing (NLP) after fine-tuning. These models, however, suffer from poor robustness and lack of interpretability. We refer to pre-trained language models with knowledge injection as knowledge-enhanced pre-trained language models (KEPLMs). These models demonstrate deep understanding and logical reasoning and introduce interpretability. In this survey, we provide a comprehensive overview of KEPLMs in NLP. We first discuss the advancements in pre-trained language models and knowledge representation learning. Then we systematically categorize existing KEPLMs from three different perspectives. Finally, we outline some potential directions of KEPLMs for future research.

关键词： natural language processing pre-trained language models symbolic knowledge knowledge enhanced pre-trained language models

来源：评论

学校读者我要写书评

暂无评论

Towards Realistic Face Photo-Sketch Synthesis via Composition-Aided GANs

arXiv

引用

arXiv 2017年

作者： Yu, Jun Shi, Shengjie Gao, Fei Tao, Dacheng Huang, Qingming Key Laboratory of Complex Systems Modeling and Simulation School of Computer Science and Technology Hangzhou Dianzi University Hangzhou310018 China State Key Laboratory of Integrated Services Networks Xidian University Xian710071 China UBTech Sydney Artificial Intelligence Institute The School of Information Technologies Faculty of Engineering and Information Technologies The University of Sydney J12 Cleveland St DarlingtonNSW2008 Australia School of Computer and Control Engineering University of Chinese Academy of Sciences Beijing100190 China

Face photo-sketch synthesis aims at generating a facial sketch/photo conditioned on a given photo/sketch. It is of wide applications including digital entertainment and law enforcement. Precisely depicting face photos/sketches remains challenging due to the restrictions on structural realism and textural consistency. While existing methods achieve compelling results, they mostly yield blurred effects and great deformation over various facial components, leading to the unrealistic feeling of synthesized images. To tackle this challenge, in this work, we propose to use the facial composition information to help the synthesis of face sketch/photo. Specially, we propose a novel composition-aided generative adversarial network (CA-GAN) for face photo-sketch synthesis. In CA-GAN, we utilize paired inputs including a face photo/sketch and the corresponding pixel-wise face labels for generating a sketch/photo. In addition, to focus training on hard-generated components and delicate facial structures, we propose a compositional reconstruction loss. Finally, we use stacked CA-GANs (SCA-GAN) to further rectify defects and add compelling details. Experimental results show that our method is capable of generating both visually comfortable and identity-preserving face sketches/photos over a wide range of challenging data. Our method achieves the state-of-the-art quality, reducing best previous Fréchet Inception distance (FID) by a large margin. Besides, we demonstrate that the proposed method is of considerable generalization ability. We have made our code and results publicly available: Https://***/ca-gan/. Copyright © 2017, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：